Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 27-TRANSCODER-HP
    4. 1047
    Prev
    Next
    INDEX
    Explanations

    say "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tober
    -0.30
    iards
    -0.27
    /cgi
    -0.26
    rzy
    -0.25
    edia
    -0.24
    ạp
    -0.24
    以人为
    -0.24
    .Pod
    -0.24
     vá
    -0.23
    ków
    -0.23
    POSITIVE LOGITS
     of
    0.56
    à¸Ĥà¸Ńà¸ĩ
    0.39
    of
    0.39
    _of
    0.37
     cá»§a
    0.35
    .of
    0.31
    Of
    0.31
    	of
    0.30
     counting
    0.27
     ol
    0.26
    Activations Density 0.010%

    No Known Activations